Bunch-by-Bunch Prediction of Beam Transverse Position, Phase, and Length in a Storage Ring Using Neural Networks

TL;DR

This paper introduces a neural network framework that accurately predicts beam transverse position, phase, and length in real-time from monitor waveforms, enhancing diagnostics and control in storage rings.

Contribution

The study develops a hybrid neural network architecture that predicts multiple beam parameters simultaneously, overcoming limitations of traditional serial and batch processing methods.

Findings

Achieves sub-millisecond prediction latency (0.042 ms per bunch)

Validated on experimental data from major synchrotron facilities

Demonstrates potential for real-time diagnostics and feedback in light sources

Abstract

Real-time, bunch-by-bunch monitoring of transverse position, longitudinal phase, and bunch length is crucial for beam control in diffraction-limited storage rings, where complex collective dynamics pose unprecedented diagnostic challenges. This study presents a neural network framework that simultaneously predicts these parameters directly from beam position monitor waveforms. The hybrid architecture integrates specialized Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN), and Long Short-Term Memory with Attention (LSTM-Attention) sub-networks, overcoming key limitations of traditional methods such as serial processing chains and batch-mode operation. Validated on experimental data from the Shanghai Synchrotron Radiation Facility and Hefei Light Source, the model achieves high prediction accuracy with a sub-millisecond latency of 0.042 ms per bunch. This performance demonstrates its potential as a core tool for real-time, multi-parameter diagnostics and active feedback in next-generation light sources.